Geometric Prior Based Deep Human Point Cloud Geometry Compression

arXiv:2305.01309v2 Announce Type: replace-cross
Abstract: The emergence of digital avatars has raised an exponential increase in the demand for human point clouds with realistic and intricate details. The compression of such data becomes challenging with overwhelming data amounts comprising millions of points. Herein, we leverage the human geometric prior in geometry redundancy removal of point clouds, greatly promoting the compression performance. More specifically, the prior provides topological constraints as geometry initialization, allowing adaptive adjustments with a compact parameter set that …

abstract arxiv avatars cloud compression cs.cv data demand digital digital avatars eess.iv emergence geometry human prior type